Download image file from the HTML page source

Here is some code to download all the images from the supplied URL, and save them in the specified output folder. You can modify it to your own needs.

"""
dumpimages.py
    Downloads all the images on the supplied URL, and saves them to the
    specified output file ("/test/" by default)

Usage:
    python dumpimages.py http://example.com/ [output]
"""
from bs4 import BeautifulSoup as bs
from urllib.request import (
    urlopen, urlparse, urlunparse, urlretrieve)
import os
import sys

def main(url, out_folder="/test/"):
    """Downloads all the images at 'url' to /test/"""
    soup = bs(urlopen(url))
    parsed = list(urlparse(url))

    for image in soup.findAll("img"):
        print("Image: %(src)s" % image)
        filename = image["src"].split("https://stackoverflow.com/")[-1]
        parsed[2] = image["src"]
        outpath = os.path.join(out_folder, filename)
        if image["src"].lower().startswith("http"):
            urlretrieve(image["src"], outpath)
        else:
            urlretrieve(urlunparse(parsed), outpath)

def _usage():
    print("usage: python dumpimages.py http://example.com [outpath]")

if __name__ == "__main__":
    url = sys.argv[-1]
    out_folder = "/test/"
    if not url.lower().startswith("http"):
        out_folder = sys.argv[-1]
        url = sys.argv[-2]
        if not url.lower().startswith("http"):
            _usage()
            sys.exit(-1)
    main(url, out_folder)

Edit: You can specify the output folder now.

Leave a Comment